Nvidia GeForce GTX 1050 Ti Scaling with FX and Ryzen on Windows 10 1703
This posting is part of a series of posts meant to explore the following topics:
- Testing designed to compare FX and Ryzen scaling with various workloads.
- Testing designed to compare GTX 660 and GTX 1050 Ti scaling with various CPUs.
- Testing designed to compare Windows 7 and Windows 10 under real-world idle conditions.
- Testing designed to compare gaming/encoding performance while encoding (under CPU load) in the background.
Level1Tech Threads:
- AMD FX 8350 versus AMD Ryzen 7 1700 Scaling on Windows 10 1703
- Windows 7 versus Windows 10 1703 Benchmarks
- Windows 10 1703 Idle versus Load Performance on FX and Ryzen
- Nvidia GeForce GTX 1050 Ti Scaling with FX and Ryzen on Windows 10 1703
External Topic Index:
- AMD FX 8350 versus AMD Ryzen 7 1700 Scaling on Windows 7
- AMD FX 8350 versus AMD Ryzen 7 1700 Scaling on Windows 10 1703
- Windows 7 Idle versus Load Performance on FX and Ryzen
- Windows 10 1703 Idle versus Load Performance on FX and Ryzen
- Windows 7 versus Windows 10 1703 Benchmarks
- Windows 7 Load versus Windows 10 1703 Load Benchmarks
- Nvidia GeForce GTX 660 Scaling with FX and Ryzen on Windows 10 1703
- Nvidia GeForce GTX 1050 Ti Scaling with FX and Ryzen on Windows 10 1703
Disclaimers
The following benchmarks were performed with the following hardware configurations:
- Windows 7 Sp1 Updated, Windows 10 1703 Updated
- GeForce GTX 660 and 1050Ti both at stock frequences.
- Tests focus on real-world configurations and actual usage variations, not solely hardware component isolation. For that, check out gamersnexus.
- 1% lows, 0.1% lows and standard deviation calculations (for accurate error bars) not performed due to data analysis and time limitations.
- For full disclaimers, detailed configuration information, and results data please see the raw results Google doc. Tabs exist.
- Regarding MetroLL and Ryzen's SMT.
Synthetic GPU Benchmarks
Passmark GPU
- Significant scaling across architectures (11.5%) but not clock speed increases.
CineBenchR15 OpenGL
- What real world applications scale like this? Maybe OpenGL games? So DOOM maybe?
3DMark Firestrike Score
- Significant scaling across both architectures and not clock speeds that is likely more indicative of real-world performance in non-GPU bound games.
3DMark TimeSpy Score
- Phenom II and older CPUs, like Brisbane, are not DX12 compatible.
Unigine-Heaven FPS
- That 4850e lives!
- More importantly, it seems getting a better CPU will increase minimum frame rates significantly.
- This test also does not properly factor in that minimum frame rate increase into how it reports averages.
Unigine-Heaven Score
- The minimums are not reflected in the score at all.
Games
Tomb Raider
- Obviously completely GPU bound.
- That 4850s is totally playable at 1080p on Ultra.
Metro Last Light
- Regarding MetroLL and Ryzen's SMT.
- Metro responds quite well to better CPU frequencies, and with SMT disabled, will likely have better performance than the FX 8350. With SMT enabled however...
- Just remember to test for this in your games and consider playing around with SMT and/or setting core affinities.
Shadow of Mordor
- GPU bound with marginal performance increases with a better CPU.
Ashes of the Singularity Escalation
- Assuming stock, Ashes shows an 8.7% Average for Heavy scenes improvement when switching from FX to Ryzen.
- Considering GPU improvements tend to be in the ballpark above 30% improvement for any given game, it seems it would still be advisable to get a better GPU instead for better performance.
- That does not hold true for the 4850e. Upgrading from a 4850e to an 8350 @ stock would yield 252% the performance.
Conclusions
- If you have an FX8350 and a 1050Ti or lower, do not expect massive performance increases switching to Ryzen. Safe yourself some money and upgrade the GPU instead.
- CPU-focused games can be a different story as well as minimums. How minimums scale with the 8350, since they are heavily influenced by the CPU in CPU bound games, is unclear.
- Minimums and the associated frame times go a long way towards making games playable, more so than averages given that they are more indicative of bad frame times and stutters.
- Based upon some benchmarks by gamers nexus: Games with an FX8370 (same CPU has 8350 with a different clock rate) and 1080 Ti can show roughly ~50% improvement when switching to an OC'd i7 7700k.
- So after combing data, the bottleneck for diminishing returns with the FX 8350 in terms of a GPU upgrade exists above the 1050 Ti and below the 1080 Ti. Maybe a 1060 6GB, 1070 or Vega would the most before further frame rate improvements percentages, relative to a GPU upgrade beyond that point, would suggest getting a better CPU instead. Again, that is true for averages, minimums are another story.
